检索结果-内蒙古大学图书馆

A reader-writer queue with reader preference

Queueing systems 1994年第1-4期15卷 81-97页

作者： Kulkarni, V.G. Puryear, Lindsey C. Department of Operations Research University of North Carolina Chapel Hill 27599 NC United States IBM Corporation Programming Systems Cary 27512 NC United States

This paper considers a reader-writer queue with reader preference. The system can process an unlimited number of readers simultaneously. However, writers have to be processed one at a time. Readers are given non-preemptive priority over writers. Both readers and writers arrive according to Poisson processes (PP) and have general independent service times. There is infinite waiting room for both. This system is analyzed to produce stability conditions. The analysis uses an M/G/∞ queue busy period to model readers, followed by a modified M/G/1 queue to model the entire system. Finally, results are presented for the expected wait-in-queue times for the readers and writers. The paper ends with an example. © 1994 J.C. Baltzer AG, Science Publishers.

关键词： concurrency control locking M/G/∞ queue M/G/1 queue with exceptional service reader preference reader-writer queue

来源：评论

学校读者我要写书评

暂无评论

Parallel genome sequence searching on supercomputer BlueGene/P

Parallel genome sequence searching on supercomputer BlueGene...

引用

作者： Borovska, Plamenka Nakov, Ognian Gancheva, Veska Georgiev, Ivailo Department of Computer Systems Technical University Sofia Bulgaria Faculty of Computer Systems and Control Technical University Sofia Bulgaria Department of Programming and Computer Technologies Technical University Sofia Bulgaria

ISBN: (纸本)9789604742509

The aim of this paper is to investigate the efficiency of sequence alignment. The parallel computational model is based on mpiBlast algorithm, data decomposition and manager-worker algorithmic paradigm utilizing massage passing based on MPI and is verified on the basis of flat parallel program implementation on a supercomputer BlueGene/P.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Lookback Period, Epochs and Hidden States Effect on Time Series Prediction Using a LSTM based Neural Network 28

Lookback Period, Epochs and Hidden States Effect on Time Ser...

引用

28th National Conference with International Participation, TELECOM 2020

作者： Koparanov, Kiril Andreev Georgiev, Krasin Krasimirov Shterev, Vasil Aleksandrov Technical University of Sofia Faculty of Computer Systems and Technologies Department of Programming and Computer Technologies 8 Kliment Ohridski blvd. Sofia1000 Bulgaria

ISBN: (纸本)9781728187174

Forecasting time series problem occurs in various subject areas. Recently neural network techniques have been used for solving such tasks. However, they have not been sufficiently studied. The article explores the influence of the lookback period, the training epochs, and hidden state dimensionality in forecasting time series using long short-term memory. Numerical experiments with example financial data show that using more lags does not improve the results. Such a study of model parameters is important for their proper selection. © 2020 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Understanding Student Success Prediction Using SHapley Additive exPlanations 11

Understanding Student Success Prediction Using SHapley Addit...

引用

11th International Scientific Conference on Computer Science, COMSCI 2023

作者： Ujkani, Berat Minkovska, Daniela Nakov, Ognyan Technical University of Sofia Faculty of Computer Systems and Technologies Department of Programming and Computer Technologies 8 Kliment Ohridski blvd. Sofia1000 Bulgaria

ISBN: (纸本)9798350325256

Predicting student success is an important task in educational institutions, as it allows for targeted interventions and support systems to enhance educational outcomes. This paper explores the use of SHAP (SHapley Additive exPlanations) model-agnostic method in understanding and interpreting student success prediction. The predictive model was built using Multi-Layer Perceptron neural network algorithm on a large public dataset. By shedding light on the underlying factors driving student success, this research contributes to the advancement of data-driven decision-making in education. © 2023 IEEE.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

Human VS AI-Generated Content: Where to Draw the Line? 33

Human VS AI-Generated Content: Where to Draw the Line?

引用

33rd International Scientific Conference Electronics, ET 2024

作者： Minkovska, Daniela V. Antonova, Elena V. Technical University of Sofia Faculty of Computer Systems and Technologies Department of Programming and Computer Technologies 8 Kliment Ohridski blvd. Sofia1000 Bulgaria

ISBN: (纸本)9798350376449

The integration and detection of AI (Artificial Intelligence) in a variety of fields, primarily education, are examined in this paper. With an emphasis on virtual assistants and their uses, it explores the potential and constraints of such technology. A study was conducted with students at the Technical University of Sofia, to assess their ability to distinguish between texts written by humans and AI. The results showcase that learners need to develop their critical analysis skills evidenced by their mixed expertise. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Software Anomaly Detection Method Based on Artificial Neural Network 20

Software Anomaly Detection Method Based on Artificial Neural...

引用

20th IEEE International Conference on e-Business Engineering, ICEBE 2024

作者： Gancheva, Veska Technical University of Sofia Faculty of Computer Systems and Technologies Department of Programming and Computer Technologies 8 Kliment Ohridski blvd. Sofia1000 Bulgaria

ISBN: (纸本)9798350365856

A growing range of data sets have been created in recent years;these are used by platforms and software applications and kept in remote access repositories. Datasets are therefore more susceptible to harmful attacks. As a result, network security in data transmission is becoming a more important area of study. One well-known method for safeguarding computer systems is the deployment of intrusion detection systems. This study proposes an artificial intelligence based method for data analysis-based anomaly detection. Methods based on machine learning and rules are mixed together. The right rules are created via a genetic algorithm. Relevant features are extracted using principal component analysis with the goal of enhancing performance. The KDD Cup 1999 dataset is used to empirically validate the suggested procedure, satisfying the criterion of using appropriate data. Using the well-known benchmark dataset, the suggested approach is used to identify and examine four different kinds of attacks: Neptune, Ipsweep, Pod, and Teardrop. During the machine learning phase, the data is categorized into categories of attacks and normal behavior after the features set during the training phase are tested. For the purpose of data analysis, the input data is divided into training and testing sets for an artificial neural network. The first 80% of the data are used to train the neural network, and the remaining 20% are used for testing. The estimated accuracy improves with the number of epochs and is higher for training data and lower for validation test data, according to experimental results. Consequently, the trained model can be retained and used to detect discrepancies. The learnt model is used to the system to compute new input parameters that are not used during training or validation. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

FormulaBuilder: A tool for graph-based modelling and generation of formulae

FormulaBuilder: A tool for graph-based modelling and generat...

引用

28th International Conference on Software Engineering 2006, ICSE '06

作者： Jörges, Sven Margaria, Tiziana Steffen, Bernhard Department of Programming Systems Otto-Hahn-Str. 14 44227 Dortmund Germany Department of Service and Software Engineering August-Bebel-Str. 89 14482 Potsdam

ISBN: (纸本)1595933751

In this paper we present the FormulaBuilder, a flexible tool for graph-based modelling and generation of formulae. The FormulaBuilder allows easy and intuitive creation of formulae by using basic components called Formula Building Blocks (FBBs) and arranging them as graphs according to the syntactic structure of a formula. Such a graph can then be validated and used to generate the corresponding formula on the basis of a specific syntax which is chosen from a list of syntaxes supported by the FormulaBuilder. An important application of the FormulaBuilder is the formal specification of properties that describe the requirements of a system. Such property specifications are usually needed by verification tools like model checkers, that help software engineers to detect errors in a specified system. The FormulaBuilder allows users to model property specifications as formula graphs by using commonly-occurring specification patterns.

关键词： Computer aided software engineering

来源：评论

学校读者我要写书评

暂无评论

The e-learning test system module for statistical analysis of tests' results 28

The e-learning test system module for statistical analysis o...

引用

28th International Scientific Conference Electronics, ET 2019 - Proceedings

作者： Stoyanova, Lyudmila Yordanova Minkovska, Daniela Veleva Percuku, Arber Shefqet Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia 8 Kliment Ohridski blvd. Sofia1000 Bulgaria

ISBN: (纸本)9781728125749

In this paper are presented the description of the developed and implemented system for tests control and the analysis of the results received from the testing of students. The database and the developed forms are revealed in the paper. Statistical and probability analysis of the received results are being made and described. Conclusions have been made for the advantages of the newly developed system. © 2019 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Development and Analysis of Genetic Algorithm for Optimization of Continuous Cast Billets Warehousing Process

Development and Analysis of Genetic Algorithm for Optimizati...

引用

2024 International Russian Smart Industry Conference, SmartIndustryCon 2024

作者： Shchegolikhin, Ivan S. Andreev, Sergey M. Nosov Magnitogorsk State Technical University Department of Computer Engineering and Programming Magnitogorsk Russia Nosov Magnitogorsk State Technical University Department of Automated Control Systems Magnitogorsk Russia

ISBN: (纸本)9798350395044

Warehouses are an important logistic component of various companies. Warehouses may have different layouts, equipment and their own features. Optimization of warehouse operations can decrease overhead costs and increase the economic efficiency of industry. The technological process of steel sheet production at a metallurgical company includes two major stages: casting of liquid steel into billets and rolling of these billets on a rolling mill. In order to coordinate the productivity of these two stages and to be able to fulfill orders promptly, a warehouse of slabs (billets) is used. Billets of different parties and steel grades are stored in stacks. The billets are moved to the warehouse for storage and from the warehouse to the rolling mill by bridge cranes. In this paper the problem of optimization of the process of continuous cast billets storage is solved to minimize the number of slab handling operations. The problem is decomposed into two subproblems SLAP (Storage Location Assignment Problem) and CSP (Crane Scheduling Problem). A modified genetic algorithm was applied to solve the problem. Using a simulation model of the warehouse, the efficiency of the algorithm was evaluated using different approaches to take the restrictions imposed on the process of slab handling into account. It is shown that the most effective is the algorithm in which there is no restriction on the placement of stacks of billets belonging to one melting. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning Techniques for Software Anomaly Detection 3

Application of Machine Learning Techniques for Software Anom...

引用

3rd International Conference on Applied Mathematics and Computer Science, ICAMCS 2023

作者： Gancheva, Veska Technical University of Sofia Faculty of Computer Systems and Technologies Department of Programming and Computer Technologies 8 Kliment Ohridski blvd. Sofia1000 Bulgaria

ISBN: (纸本)9798350324266

A rising variety of platforms and software programs have leveraged repository-stored datasets and remote access in recent years. As a result, datasets are more vulnerable to malicious attacks. As a result, network security has grown in importance as a research topic. The usage of intrusion detection systems is a well-known strategy for safeguarding computer networks. This paper proposes an anomaly detection method that blends rule-based and machine-learning-based methods. In order to construct the appropriate rules, a genetic algorithm is utilized. Principal component analysis is used to extract the relevant features aimed to improve the performance. The suggested method is validated experimentally using the KDD Cup 1999 dataset, which meets the requirement of using appropriate data. The proposed method is applied to detect and analyze four types of attacks in a well-known benchmark dataset: Neptune, Ipsweep, Pod, and Teardrop, utilizing Support Vector Machine, Decision Tree, and Naive Bayes algorithms. After testing the characteristics specified in the training phase, the data is classified into attack categories and normal behavior during the machine learning phase. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：